mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-22 06:00:00 +08:00
77f0fb03e3
### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
46 lines
1.8 KiB
Python
46 lines
1.8 KiB
Python
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from rag.nlp import find_codec,num_tokens_from_string
|
|
import re
|
|
|
|
class RAGFlowTxtParser:
|
|
def __call__(self, fnm, binary=None, chunk_token_num=128, delimiter="\n!?;。；！？"):
|
|
txt = ""
|
|
if binary:
|
|
encoding = find_codec(binary)
|
|
txt = binary.decode(encoding, errors="ignore")
|
|
else:
|
|
with open(fnm, "r") as f:
|
|
while True:
|
|
l = f.readline()
|
|
if not l:
|
|
break
|
|
txt += l
|
|
return self.parser_txt(txt, chunk_token_num, delimiter)
|
|
|
|
@classmethod
|
|
def parser_txt(cls, txt, chunk_token_num=128, delimiter="\n!?;。；！？"):
|
|
if type(txt) != str:
|
|
raise TypeError("txt type should be str!")
|
|
sections = []
|
|
for sec in re.split(r"[%s]+"%delimiter, txt):
|
|
if sections and sec in delimiter:
|
|
sections[-1][0] += sec
|
|
continue
|
|
if num_tokens_from_string(sec) > 10 * int(chunk_token_num):
|
|
sections.append([sec[: int(len(sec) / 2)], ""])
|
|
sections.append([sec[int(len(sec) / 2) :], ""])
|
|
else:
|
|
sections.append([sec, ""])
|
|
return sections |